© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253445
    Prev
    Next
    INDEX
    Explanations

    py

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    0.39
     Most
    0.36
     impot
    0.36
     forced
    0.36
     spoiled
    0.35
     ज्व
    0.35
     intellectual
    0.33
     psycho
    0.32
    <code>
    0.32
    vole
    0.32
    POSITIVE LOGITS
    ربی
    0.40
     الالكتروني
    0.38
    楕
    0.38
    ૄ
    0.38
    ্চ
    0.36
    currentItem
    0.36
    гӀ
    0.36
    Tres
    0.36
    Conteudos
    0.35
    র্কে
    0.35
    Activations Density 0.001%

    No Known Activations